Brainco

Security Engineer, AI Platform

San Francisco Bay Area, Remote. Posted a month ago

The role

A Platform Security Engineer will design and ship code to build guardrails for AI agents. You will build services for scoped permissions, data access controls, and tool-call validation to protect sensitive customer data.

What you will do

  • Design and build guardrail services for AI agent actions, permissions, and tool-call validation
  • Write production code for data access controls to protect PII and sensitive records
  • Build reusable guardrail libraries and SDKs for product engineers
  • Design detection and containment for prompt injection, tool misuse, and data exfiltration
  • Build automated tests and red-team harnesses
  • Instrument agents with tamper-evident audit logs and decision trails
  • Partner with product, platform and ML engineering to review agent capabilities
  • Own the developer experience for guardrails including APIs and documentation
  • Help define and measure guardrail effectiveness and coverage

Required qualifications

  • 5 to 8 years as a software engineer building and shipping production systems
  • Meaningful time spent on security, data protection, or trust & safety problems
  • Strong general-purpose programming skills (Python, Go, TypeScript, or similar)
  • Experience with or strong working knowledge of how AI agents operate in production
  • Knowledge of tool use, function calling, or orchestration frameworks (LangChain, LangGraph, or similar)
  • Solid grasp of data protection fundamentals including PII handling, access control, encryption, and least privilege
  • Working cloud experience (AWS, GCP, or Azure)
  • Comfortable across the SDLC
  • Strong written English

Nice to have

  • Direct experience building guardrails or safety layers for LLM/agent systems
  • Background in regulated industries (healthcare, government, financial services)
  • Familiarity with policy-as-code, secrets management, or software supply-chain security tooling
  • Prior startup experience

Benefits

  • Meaningful equity
  • Country-specific benefits

Before you apply

  • Send your CV and a brief note on a guardrail, safety control, or piece of security tooling you’ve built

About the company

Brain Co. builds AI-native operating systems for large, regulated institutions. Their proprietary platform is called Atlas.